Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.1
Journals
Algorithms
Special Issues
Explainable AI: Advances in Interpretability Algorithms and Applications
share announcement

Explainable AI: Advances in Interpretability Algorithms and Applications

A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 3689

Special Issue Editor

Prof. Dr. Antonio Sarasa-Cabezuelo

E-Mail Website
Guest Editor
Facultad de Informática, Universidad Complutense de Madrid, 28001 Madrid, Spain
Interests: machine learning; artificial intelligence; e-learning; programming languages
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The growing integration of artificial intelligence (AI) in critical domains such as healthcare, finance, law, and autonomous systems has intensified the need for models that are not only accurate, but also interpretable and transparent. In response, explainable artificial intelligence (XAI) has emerged as a field dedicated to opening the “black box” of complex AI systems, enabling human users to understand, trust, and effectively govern intelligent algorithms.

This Special Issue will focus on recent advances in explainability algorithms—both model-specific and model-agnostic—that aim to improve the transparency, accountability, and robustness of AI systems across diverse applications. As AI continues to be deployed in high-stakes environments, the development of reliable interpretability tools becomes essential for ensuring ethical use, regulatory compliance, and human-centric design.

We invite high-quality submissions that address the theoretical foundations, algorithmic innovations, and real-world implementations of explainable AI. We particularly welcome interdisciplinary research that bridges technical development with societal, legal, or ethical considerations.

Topics of interest include, but are not limited to, the following:

  • Novel algorithms for local and global interpretability;
  • Comparative studies of XAI methods (e.g., SHAP, LIME, Integrated Gradients, Anchors);
  • Benchmarks, metrics, and evaluation frameworks for XAI;
  • Explainability in ensemble learning, deep learning, and generative models;
  • Interpretable AI in healthcare, finance, law, and scientific discovery;
  • Human-in-the-loop and interactive explanations;
  • Visualization techniques for explainable AI;
  • The role of explainability in AI ethics, fairness, and accountability;
  • Regulatory perspectives and standards for transparent AI;
  • Robustness and reliability of explanation methods under adversarial conditions;
  • Causal inference and counterfactual reasoning in XAI;
  • Usability and cognitive dimensions of model explanations;
  • Explainability in edge computing, IoT, and real-time systems.

We welcome original research articles, surveys, case studies, and critical reviews that contribute to advancing the field of interpretable and explainable artificial intelligence.

Dr. Antonio Sarasa-Cabezuelo
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • explainable AI (XAI)
  • interpretability algorithms
  • SHAP, LIME, Anchors
  • transparent machine learning
  • trustworthy AI
  • human-centered AI
  • algorithmic accountability
  • model-agnostic explainability
  • fairness and bias in AI
  • XAI for high-stakes applications
  • AI ethics and governance
  • interpretable deep learning
  • AI transparency frameworks
  • responsible AI design

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

29 pages, 3934 KB  
Article
Explainability as a Structural Property: An Empirical Analysis of Rashomon Sets and Pareto Fronts
by Roberto Stevens Porto Solano, Antonio Berlanga de Jesús, José M. Molina López Berlanga and Yair Rivera Julio
Algorithms 2026, 19(5), 358; https://doi.org/10.3390/a19050358 - 4 May 2026
Abstract
While most current work on interpretable models has centered on post hoc explainability of individual predictive models, the structure of the hypothesis space from which such models are drawn has been largely neglected. This paper proposes a contrasting perspective in which explainability is [...] Read more.
While most current work on interpretable models has centered on post hoc explainability of individual predictive models, the structure of the hypothesis space from which such models are drawn has been largely neglected. This paper proposes a contrasting perspective in which explainability is treated not as an attribute of a single solution but as a structural property of the model space. By combining Rashomon set analysis with Pareto-based performance–model complexity trade-offs, we formulate a computational framework for identifying near-optimal and structurally simple models. A performance–model complexity trade-off landscape is constructed by systematically generating models under controlled complexity bounds and extracting Pareto-optimal solutions. The results show that explainability can emerge as a regional property of hypothesis spaces in which multiple interpretable models achieve competitive predictive performance. This perspective supports the identification of robust and auditable predictive solutions and complements traditional explainability approaches centered on isolated models. Cross-dataset replication on Wine (UCI) and Vehicle (UCI) confirms the generalizability of these findings. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
23 pages, 313 KB  
Article
Trust, Education, and Artificial Intelligence: Adoption, Explainability, and Epistemic Authority Among Teacher-Education Undergraduates in Greece
by Epameinondas Panagopoulos, Charalampos M. Liapis, Anthi Adamopoulou, Ioannis Kamarianos and Sotiris Kotsiantis
Algorithms 2026, 19(5), 350; https://doi.org/10.3390/a19050350 - 1 May 2026
Viewed by 137
Abstract
This study investigates how teacher-education undergraduates in Greece use, evaluate, and trust Artificial Intelligence (AI) in higher education, with particular attention to the gap between widespread adoption and limited epistemic trust. The topic is important because generative AI is rapidly entering universities, reshaping [...] Read more.
This study investigates how teacher-education undergraduates in Greece use, evaluate, and trust Artificial Intelligence (AI) in higher education, with particular attention to the gap between widespread adoption and limited epistemic trust. The topic is important because generative AI is rapidly entering universities, reshaping learning practices, academic integrity, and the legitimacy of knowledge, while learners often rely on systems whose outputs are not easily verifiable. The study focuses on future teachers because they are both current users of AI in higher education and likely future mediators of its use in school settings. Addressing this problem, the study contributes empirical evidence on how AI adoption relates to epistemic authority and institutional legitimacy within teacher education rather than across university students in general. A mixed-methods design was employed using a structured questionnaire completed by 363 teacher-education undergraduates from the University of Patras and the University of Ioannina in Greece; the sample was predominantly women (86.0%) and first-year students (92.6%). Quantitative responses were analyzed statistically, open-ended answers were examined thematically, and factor analysis was used to identify latent attitudinal dimensions. The findings indicate very high AI use in everyday life (92.6%) and study practices (81.3%), but only moderate trust: 1.4% reported complete trust and 12.1% generally trusted AI-generated answers. Six dimensions explained 61.73% of total variance, pointing to a layered attitudinal structure within this teacher-education population, consistent with an adoption–trust paradox and with the need for transparent, verifiable, human-supervised educational AI. The observed verification-based trust calibration may partly reflect an emerging pedagogical orientation toward source checking and responsibility for knowledge mediation, but given the strong concentration of first-year students, this should be interpreted as characteristic of early-stage teacher education rather than of university students more broadly. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
►▼ Show Figures

Graphical abstract

23 pages, 955 KB  
Article
Scalable Bayesian–XAI Framework for Multi-Objective Decision-Making in Uncertain Dynamic Systems
by Mostafa Aboulnour Salem and Zeyad Aly Khalil
Algorithms 2026, 19(5), 340; https://doi.org/10.3390/a19050340 - 28 Apr 2026
Viewed by 165
Abstract
This study proposes a scalable Explainable Artificial Intelligence (XAI)–driven Bayesian–AI decision–control framework for multi-objective optimisation in uncertain and dynamic systems. The framework integrates Bayesian networks, stochastic control, and expected utility theory within a unified probabilistic architecture. Unlike traditional black-box models, the proposed framework [...] Read more.
This study proposes a scalable Explainable Artificial Intelligence (XAI)–driven Bayesian–AI decision–control framework for multi-objective optimisation in uncertain and dynamic systems. The framework integrates Bayesian networks, stochastic control, and expected utility theory within a unified probabilistic architecture. Unlike traditional black-box models, the proposed framework provides intrinsic interpretability through probabilistic reasoning and dependency-aware modelling. This allows users to understand how decisions are formed and how variables influence outcomes. To further strengthen explainability, the framework incorporates post hoc XAI techniques, including SHAP-based feature attribution and sensitivity-based local explanations. These methods quantify the contribution of each variable and provide clear explanations at both global and local levels. The system is formulated as a stochastic state-space model and implemented as a closed-loop adaptive architecture. It updates decisions continuously as new data becomes available. Scalable inference is achieved using variational inference, Markov Chain Monte Carlo, and Sequential Monte Carlo methods. This ensures efficient performance in complex and high-dimensional environments. A simulation study based on 370 observations shows that the proposed framework improves decision quality, robustness under uncertainty, and transparency compared to conventional methods. Explainability is evaluated using Fidelity, Stability, and Transparency metrics. The results confirm that the model produces consistent and reliable explanations. The framework supports human-centred decision-making by providing visual analytics and clear probabilistic explanations. This makes it suitable for high-stakes applications such as cyber–physical systems, intelligent platforms, and real-time AI systems. The main contribution of this study is the integration of intrinsic probabilistic interpretability with post hoc XAI techniques into a single, scalable framework. This approach bridges a key gap in XAI research and offers a practical and transparent solution for decision-making under uncertainty. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
29 pages, 7418 KB  
Article
EvoDropX: Evolutionary Optimization of Feature Corruption Sequences for Faithful Explanations of Transformer Models
by Dhiraj Kumar Singh and Conor Ryan
Algorithms 2026, 19(3), 187; https://doi.org/10.3390/a19030187 - 2 Mar 2026
Viewed by 396
Abstract
As deep learning models become increasingly integrated into critical decision-making systems, the need for explainable Artificial Intelligence (xAI) has grown paramount to ensure transparency, accountability, and trust. Post hoc explainability methods, which analyse trained models to interpret their predictions without modifying the underlying [...] Read more.
As deep learning models become increasingly integrated into critical decision-making systems, the need for explainable Artificial Intelligence (xAI) has grown paramount to ensure transparency, accountability, and trust. Post hoc explainability methods, which analyse trained models to interpret their predictions without modifying the underlying architecture, have become increasingly important, especially in fields such as healthcare and finance. Modern xAI techniques often produce feature importance rankings that fail to capture the true causal influence of features, particularly in transformer-based models. Recent quantitative metrics, such as Symmetric Relevance Gain (SRG), which measures the area between the feature corruption performance curves of the Most Important Feature (MIF) and the Least Important Feature (LIF), provide a more rigorous basis for evaluating explanation fidelity. In this study, we first show that existing xAI methods exhibit consistently poor performance under the SRG criterion when explaining transformer-based text classifiers. To address these limitations, we introduceEvoDropX, a novel framework that formulates explanation as an optimisation problem. EvoDropX leverages Grammatical Evolution (GE) to evolve sequences of feature corruption with the explicit objective of maximising SRG, thereby identifying features that most strongly influence model predictions. EvoDropX provides interventional, input–output (behavioural) explanations and does not attempt to infer or interpret internal model mechanisms. Through comprehensive experiments across multiple datasets (IMDb movie reviews (IMDB), Stanford Sentiment Treebank (SST-2), Amazon Polarity (AP)), multiple transformer models (Bidirectional Encoder Representations from Transformers (BERT), RoBERTa, DistilBERT), and multiple metrics (SRG, MIF, LIF, Counterfactual Conciseness (CFC)), we demonstrate that EvoDropX significantly outperforms all state-of-the-art (SOTA) xAI baselines including Attention-Aware Layer- Wise Relevance Propagation for Transformers (AttnLRP), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-agnostic Explanations (LIME), when evaluated using intervention-based faithfulness criteria. Notably, EvoDropX achieves 74.77% improvement in SRG than the best-performing baseline on the IMDB dataset with the BERT model, with consistent improvements observed across all dataset-model pairs. Finally, qualitative and linguistic analyses reveal that EvoDropX captures both sentiment-bearing terms and their structural relationships within sentences, yielding explanations that are both faithful and interpretable. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
►▼ Show Figures

Figure 1

28 pages, 2296 KB  
Article
Interpretable Machine Learning-Based Differential Diagnosis of Hip and Knee Osteoarthritis Using Routine Preoperative Clinical and Laboratory Data
by Zhanel Baigarayeva, Baglan Imanbek, Assiya Boltaboyeva, Bibars Amangeldy, Nurdaulet Tasmurzayev, Kassymbek Ozhikenov, Daulet Baimbetov, Roza Beisembekova and Naoya Maeda-Nishino
Algorithms 2026, 19(1), 24; https://doi.org/10.3390/a19010024 - 25 Dec 2025
Viewed by 874
Abstract
Osteoarthritis (OA) of the hip (coxarthrosis) and knee (gonarthrosis) is a leading cause of disability worldwide. Differential diagnosis typically relies on imaging modalities such as X-rays and Magnetic Resonance Imaging (MRI). However, advanced imaging can be expensive and inaccessible, highlighting the need for [...] Read more.
Osteoarthritis (OA) of the hip (coxarthrosis) and knee (gonarthrosis) is a leading cause of disability worldwide. Differential diagnosis typically relies on imaging modalities such as X-rays and Magnetic Resonance Imaging (MRI). However, advanced imaging can be expensive and inaccessible, highlighting the need for non-invasive diagnostic tools. This study aimed to develop and validate an interpretable machine learning model to distinguish between hip and knee osteoarthritis using standard preoperative clinical and laboratory data. This model is designed to assist physicians in prioritizing whether to order a hip or a knee X-ray first, thereby saving time and medical resources. The study utilized retrospective data from 1792 patients treated at the City Clinical Hospital in Almaty, Kazakhstan. After applying inclusion and exclusion criteria, five machine learning algorithms were used for training and evaluation: Decision Tree, Random Forest, Logistic Regression, XGBoost, and CatBoost. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were employed to interpret predictions and determine the contribution of each feature. The XGBoost model demonstrated the best performance, achieving an accuracy of 93.85%, a precision of 95.15%, a recall of 90.51%, and an F1-score of 92.41%. SHAP analysis revealed that age, glucose and leukocyte levels, urea, and BMI made the greatest contributions to the model’s predictions, while local analysis using LIME indicated that age, leukocyte levels, glucose, erythrocytes, and platelets were the most influential features. These findings support the use of machine learning for cost-effective early osteoarthritis triage using routine preoperative data. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
►▼ Show Figures

Figure 1

20 pages, 1224 KB  
Article
Explainable AI for Coronary Artery Disease Stratification Using Routine Clinical Data
by Nurdaulet Tasmurzayev, Baglan Imanbek, Assiya Boltaboyeva, Gulmira Dikhanbayeva, Sarsenbek Zhussupbekov, Qarlygash Saparbayeva and Gulshat Amirkhanova
Algorithms 2025, 18(11), 693; https://doi.org/10.3390/a18110693 - 3 Nov 2025
Viewed by 1342
Abstract
Background: Coronary artery disease (CAD) remains a leading cause of morbidity and mortality. Early diagnosis reduces adverse outcomes and alleviates the burden on healthcare, yet conventional approaches are often invasive, costly, and not always available. In this context, machine learning offers promising solutions. [...] Read more.
Background: Coronary artery disease (CAD) remains a leading cause of morbidity and mortality. Early diagnosis reduces adverse outcomes and alleviates the burden on healthcare, yet conventional approaches are often invasive, costly, and not always available. In this context, machine learning offers promising solutions. Objective: The objective of this study is to evaluate the feasibility of reliably predicting both the presence and the severity of CAD. The analysis is based on a harmonized, multi-center UCI dataset that includes cohorts from Cleveland, Hungary, Switzerland, and Long Beach. The work aims to assess the accuracy and practical utility of models built exclusively on routine tabular clinical and demographic data, without relying on imaging. These models are designed to improve risk stratification and guide patient routing. Methods and Results: The study is based on a uniform and standardized data processing pipeline. This pipeline includes handling missing values, feature encoding, scaling, an 80/20 train–test split and applying the SMOTE method exclusively to the training set to prevent information leakage. Within this pipeline, a standardized comparison of a wide range of models (including gradient boosting, tree-based ensembles, support vector methods, etc.) was conducted with hyperparameter tuning via GridSearchCV. The best results were demonstrated by the CatBoost model: accuracy—0.8278, recall—0.8407, and F1-score—0.8436. Conclusions: A key distinction of this work is the comprehensive evaluation of the models’ practical suitability. Beyond standard metrics, the analysis of calibration curves confirmed the reliability of the probabilistic predictions. Patient-level interpretability using SHAP showed that the model relies on clinically significant predictors, including ST-segment depression. Calibrated and explainable models based on readily available data are positioned as a practical tool for scalable risk stratification and decision support, especially in resource-constrained settings. Full article
(This article belongs to the Special Issue Explainable AI: Advances in Interpretability Algorithms and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop